Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/paultyng/skill-issue/create-decision-documentnpx skills add paultyng/skill-issue --skill create-decision-documentgit clone --depth 1 https://github.com/paultyng/skill-issueWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.00437 |
| Opus 5 | $0.00024 | $0.00218 |
| Sonnet 5 | $0.00010 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
create-decision-document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Create Decision Document
Create or update a decision document in Notion using the Notion MCP.
1. Gather Context
Determine from the user:
- Title: what decision is being made
- Location: which Notion page or database to create under (ask if unclear)
- Options: the alternatives being evaluated (may emerge during research)
2. Research (if needed)
If the user asks for research before writing:
- Use Sourcegraph for organization's codebase patterns and precedent
- Use web search for external APIs, standards, and vendor comparisons
- Use Notion for existing internal docs and prior decisions
- Be terse in research summaries
3. Create the Document
Use the Notion MCP to create a page with this structure:
# <Decision Title>
## Problem Statement
<1-2 sentences describing what needs to be decided and why>
## Options
### Option A: <Name>
**Pros**
- <terse bullet>
- <terse bullet>
**Cons**
- <terse bullet>
- <terse bullet>
### Option B: <Name>
**Pros**
- <terse bullet>
**Cons**
- <terse bullet>
## Recommendation
<Which option and why, 1-2 sentences>
Formatting rules:
- Be terse throughout. No filler.
- Do not prefix Pros/Cons items with "Good:" or "Bad:".
- Bullet points, not prose paragraphs.
- If there are criteria or requirements, use a comparison table rather than repeating them per option.
4. Follow-up
Common follow-up actions (do only if asked):
- Link a PR to the decision doc
- Update the recommendation after discussion
- Add a "Decision" or "Status" field marking the choice as final
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 69 lines · 49 tokens per session scan A abc6b0d7c2ec
create-decision-document is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 437 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tdd-workflow
Test-driven development workflow.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
expert
Base expert skill.
alpha
Alpha skill.
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.